Intelligent computing paradigm for unsteady magneto nano-polymeric Casson nanofluid with Ohmic dissipation and thermal radiation

Abstract

In this present investigative mode of study, a biological innovational approach is adopted in the form of an intelligent computing paradigm to investigate the properties of flow in the case of incompressible magneto nano-polymeric Casson nanofluid using a stochastic numerical technique named artificial neural networks based on the hybridization of genetic algorithms with highly efficient local search solvers which is sequential quadratic programming. The governing PDEs of the suggested fluid model are first converted into a system of ODEs using appropriate similarity transformations and then solved for sundry scenarios generated based on physical parameters existing in the ODEs to examine the velocity profile, thermal profile and nanofluid concentration. Furthermore, by uplifting the value of Casson parameter, the temperature of the nanofluid hikes however this effect is reversed in case of radiation parameter. The strong motivation behind this study is to obtain the numerical solution of a system of nonlinear differential equations involving fifth-order derivatives with strong accuracy. A comprehensive error analysis based on tables and graphs is presented to further enhance the scientific significance of this research in the results and discussion section.